Evaluation request
#195
by
MoonRide
- opened
Hi there. I was recently playing with merging 3B models with goal of maximizing my own benchmark. It did quite well (for a 3B) there, but I would like to see how this merge performs against other non-academic benchmarks, like the one of yours :).
Links:
https://huggingface.co/MoonRide/Llama-3.2-3B-Khelavaster
https://huggingface.co/MoonRide/Llama-3.2-3B-Khelavaster-GGUF
https://ollama.com/moonride/khelavaster
DontPlanToEnd
changed discussion status to
closed